Collaborative Research: HCC: MEDIUM: Body as Intervention: Toward Closed-Loop, Embodied Behavioral Health Interventions

在美国，压力和焦虑急剧增加，导致心理健康大流行。现在比以往任何时候都更加迫切需要有效的精神卫生干预措施。通过可穿戴设备和物联网（IoT）设备监测用户的症状及其情况（例如，当某人焦虑发作或在经过酒吧时感到渴望），移动健康（mHealth）技术有可能改变精神卫生保健。尽管具有先进的监测能力，但大多数现有的移动健康干预措施都是传统健康干预措施的数字化，不能针对用户的症状提供即时精确的干预措施。因此，他们继承了前人的局限性：依赖于人的动机，需要积极参与才能有效，这导致了有限的依从性。为了解决这个问题，研究人员将开发一类新的解决方案——感官干预——它可以在不干扰用户或要求他们积极参与的情况下有效。感官干预是一种实时闭环系统，它根据用户的行为或生理信号直接作用于用户的身体或周围环境。与现有的解决方案不同，感官干预结合了应用工程、信号处理和机器学习，无需用户干预即可自动触发干预。该项目将创建三种类型的闭环可穿戴和物联网系统，使用不同的模式（振动、气流和触摸）在心理健康环境中提供感官干预，如渴望、工作压力和社会压力。最终，该项目将使移动医疗干预措施像移动医疗监测解决方案一样丰富、多样和个性化。这个项目将产生开源软件、硬件设计和数据集。与康奈尔科技精准健康计划、芝加哥大学医学院及其临床和行业合作伙伴的合作将通过临床评估和商业化加速研究的传播。大多数现有的移动健康行为干预措施，虽然与先进的传感系统相结合，以检测健康需求，但需要有意识的信息认知处理和用户的积极参与才能有效。本项目将介绍和发展感官干预的概念，这是一种新型的移动健康干预，只需很少或不需要认知意识即可有效。本项目将分四个阶段探讨感官干预：(i)调查和绘制外部（机电）刺激的模式，以驱动产生神经生理效应的神经反应；（ii）设计和开发能够在移动健康约束下实现这些感官干预的设备；（iii）确定与目标行为相关的生理信号，并整合传感系统、信号处理；通过感官干预的机器学习实现自动触发干预的闭环系统，以及（iv）评估闭环系统的有效性，可用性和可接受性（实验室和现场）。在整个过程中，研究人员将评估和描述感官干预如何影响三种常见的压力引起的心理健康挑战：物质渴望、工作压力和社会压力。为了干预对物质的渴望，研究人员将利用心率生物反馈，开发一种基于智能手表的系统，通过振动感应器提供生物反馈，并评估这种振动触觉驱动如何减轻对酒精和尼古丁的渴望。为了干预工作压力，调查人员将利用呼吸规则，开发一种基于风扇的系统，改变鼻子周围气流的感知，并评估这些气流是如何在工作场所引导缓慢呼吸的。为了干预社会压力，研究人员将利用情感触摸，开发一种激活情感触摸神经元的穿戴设备，并评估情感触摸如何帮助调节社会压力。总的来说，这项研究将使一类新的移动健康干预措施能够实时响应用户的健康状况，并且无论用户的认知能力或可用性如何，都可以有效。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

There has been a drastic increase in stress and anxiety in the U.S., leading to a mental health pandemic. The need for effective mental health interventions is more urgent now than ever. By monitoring users' symptoms and their context (e.g., when someone is having an anxiety attack or experiencing cravings when passing by a bar) through wearables and IoT (Internet of Things) devices, mobile health (mHealth) technologies have the potential to transform mental health care. Despite the advanced monitoring capability, most existing mHealth interventions are digitization of traditional health interventions that do not deliver in-the-moment precision interventions in response to users' symptoms. As such, they inherit the limitations of their predecessors: the reliance on human motivation and the need for active engagement to be effective, resulting in limited adherence. To address this problem, the investigators will develop a class of novel solutions – sensory interventions – that can be effective without disrupting the users or requiring their active engagement. Sensory interventions are real-time closed-loop systems that directly act on the users’ bodies or immediate environment in response to users behavioral or physiological signals. Unlike existing solutions, sensory interventions combine applied engineering, signal processing, and machine learning to trigger interventions autonomously without user effort. The project will create three types of closed-loop wearable and IoT systems that use different modalities (vibration, airflow, and touch) to deliver sensory interventions in mental health contexts, such as cravings, workplace stress, and social stress. Ultimately, this project will enable mHealth interventions to be as rich, diverse, and personalized as mHealth monitoring solutions. This project will produce open-source software, hardware designs, and datasets. Collaborations with Cornell Tech Precision Health Initiative and with the University of Chicago Medicine and their clinical and industry partners will accelerate the dissemination of research through clinical evaluations and commercialization. Most existing mHealth behavioral health interventions, although coupled with advanced sensing systems to detect health needs, require conscious cognitive processing of information and active participation from users to be effective. This project will introduce and develop the concept of sensory interventions, a novel class of mHealth interventions that require little or no cognitive awareness to be effective. This project will investigate sensory interventions in four stages: (i) investigate and map modalities of external (electromechanical) stimuli to actuate neurological responses that produce a neurophysiological effect (ii) design and develop devices that enable these sensory interventions within the constraints of mHealth, (iii) determine physiological signals that are associated with target behaviors and integrate sensing systems, signal processing, and machine learning with sensory interventions to achieve closed-loop systems that automatically triggers intervention, and (iv) evaluate the efficacy, usability, and acceptability of the closed-loop systems (both in-lab and in situ). Throughout this process, the investigators will evaluate and characterize how sensory interventions impact three common stress-induced mental health challenges: substance cravings, workplace stress, and social stress. To intervene in substance cravings, the investigators will leverage heart rate biofeedback, develop a smartwatch-based system to deliver biofeedback using vibrotactors, and evaluate how such vibrotactile actuation mitigates alcohol and nicotine cravings. To intervene in workplace stress, the investigators will leverage breathing regulations, develop a fan-based system that alters the perception of airflow around the nose, and evaluate how such airflow entrains slow, guided breathing in the workplace. To intervene in social stress, the investigators will leverage affective touch, develop an arm-worn device that activates affective touch neurons, and evaluate how affective touch helps regulate social stress. Collectively, this research will enable a new class of mHealth interventions that are responsive to users’ health context in real-time and can be effective irrespective of users cognitive capacity or availability.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.